Please predict the next word.

Intelligence is implicit in language understanding. The best possible next-word-predictor is omniscient.

You either have to accept the legal and moral consequences that your platform will be used for illegal things, or make your platform less safe, private, and anonymous.

Much like in the article, abliterated Qwen will not obey restrictions on its behavior encoded in the prompt. If you want something not to happen, it better be enforced in the harness or environment (e.g. sandbox). It is much different than the Anthropic models I'm used to, which will, the vast majority of time, follow rules (before auto mode, I used to always run them in "yolo" mode).

I am curious whether there's a connection between abliteration and rule following. These abliterated models are the ones you most want to follow your rules.

I find it impressive that these pocket computers are running at almost 5 GHz now.

How would one prevent the watcher from being influenced in the same way by the agent being watched?

You can also just delegate this to subagents with Claude Code (though you have a more limited choice of models unless you swap the cheaper models via OpenRouter).

I'm OK using a dumb model as a smart grep, but the whole point of using the frontier models is using their intelligence for the hard stuff like coding.

I don't see how this is any different, other than the second-level domain owner delegates their registrar job to the first-level domain owner.

There is something weird though if you control smith.name, that you don't control john.smith.name. The DNS system does convey some indirect concept of responsibility.

Yikes.